Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.
| Charge | Agents | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.11 | $0.099 | per 1M tokens |
| Outputper 1M tokens | $0.41 | $0.38 | per 1M tokens |
| Cached inputper 1M tokens | $0.060 | $0.055 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.11 in and $0.41 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| Reka, answering | 99.9% | 262K |
| DeepInfraTurbofp4, answering | 99.3% | 262K |
| CoreWeaveFp4fp4, answering | 99.5% | 262K |
| VeniceFp4fp4, answering | 99.2% | 256K |
| ChutesFp4fp4, having trouble | 95.2% | 131K |
| DeepInfraFp8fp8, answering | 98% | 262K |
| CrusoeBf16bf16, answering | 99.7% | 262K |
| Friendli, answering | 99.3% | 262K |
| NovitaBf16bf16, having trouble | 88.7% | 262K |
| ParasailFp8fp8, answering | 99.2% | 262K |
| DeepInfraUltrafp8, answering | 81.5% | 131K |
| Io Net, answering | 97.6% | 262K |
| SambaNova, answering | 97.2% | 131K |
| ModelRunFp4fp4, answering | 99.3% | 262K |
| SiliconFlowFp8fp8, answering | 94.2% | 262K |